Abstract
Drones are becoming increasingly popular not only for recreational purposes but in day-to-day applications in engineering, medicine, logistics, security and others. In addition to their useful applications, an alarming concern in regard to the physical infrastructure security, safety and privacy has arisen due to the potential of their use in malicious activities. To address this problem, we propose a novel solution that automates the drone detection and identification processes using a drone’s acoustic features with different deep learning algorithms. However, the lack of acoustic drone datasets hinders the ability to implement an effective solution. In this paper, we aim to fill this gap by introducing a hybrid drone acoustic dataset composed of recorded drone audio clips and artificially generated drone audio samples using a state-of-the-art deep learning technique known as the Generative Adversarial Network. Furthermore, we examine the effectiveness of using drone audio with different deep learning algorithms, namely, the Convolutional Neural Network, the Recurrent Neural Network and the Convolutional Recurrent Neural Network in drone detection and identification. Moreover, we investigate the impact of our proposed hybrid dataset in drone detection. Our findings prove the advantage of using deep learning techniques for drone detection and identification while confirming our hypothesis on the benefits of using the Generative Adversarial Networks to generate real-like drone audio clips with an aim of enhancing the detection of new and unfamiliar drones.
Highlights
We extend our study in this work to investigate what role, if any, the introduction and usage of an artificial dataset generated through Generative Adversarial Network (GAN) plays in improving the overall performance of the deep learning models as well as to verify if the artificially generated data will be good enough to fill the gap in drone audio datasets
We address the issue of illegal use of drones in malicious activities by proposing a novel approach that automates the drone detection and identification processes using the drone’s acoustic features with different deep learning algorithms
The lack of acoustic drone datasets restricts the ability to implement an effective solution using deep learning algorithms. Our work targets this gap by introducing a hybrid drone acoustic dataset, RG, composed of recorded drone audio clips and artificially generated drone audio clips using the Generative Adversarial Network (GAN)
Summary
Drones were mainly used for cinematography and recreational purposes; their usage has been extended to automate day-to-day operations such as vegetation monitoring [1], various wildfire mapping applications [2], precision agriculture [3] and flying over dangerous and out-of-reach areas for search and rescue missions [4]. In addition to their useful applications, their use in malicious activities to invade privacy, security and safety regulations has been increasing alarmingly. Another incident was reported in which an explosive-equipped drone was hovering over a great crowd in a formal occasion in Venezuela, targeting a high profile personnel and the general public
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
